Auto-generation of support trees

Abstract

Programs, systems, and methods for generating a support tree for automated resolution of user issues. In some embodiments, historical data may be obtained from a history of support interactions including historical issues and solutions to the historical issues. Most used solutions may be determined and stored with associated historical issues. Clusters of issues and solutions may be generated and labeled for generation of support tree nodes. Furthermore, solutions may be correlate such that a plurality of solutions may be provided for the resolving user issues. In some embodiments, issue data indicative of user issues may be provided by users. As the user provides issue data, deflections between nodes on the support tree may narrow a field of potential solutions to one or more solutions to be provided to the user.

Having thus described various embodiments of the disclosure, what is claimed as new and desired to be protected by Letters Patent includes the following: 
     
       1. A method comprising:
 obtaining historical data comprising a history of support interactions including historical issues and prior solutions to the historical issues; 
 determining a number of most used prior solutions from the prior solutions to the historical issues; 
 determining correlations between the most used prior solutions; 
 generating clusters of the most used prior solutions and one or more associated historical issues; 
 determining keywords from the historical issues and associated most used prior solutions; 
 generating labels for each cluster based on the determined keywords; 
 generating a plurality of questions to be presented to a user to obtain issue information from the user, each question associated with at least one cluster; and 
 automatically generating, using one or more computing device, a support tree comprising a plurality of clusters of nodes, each cluster containing a plurality of nodes, a label for the cluster from the generated labels, and an associated question of the plurality of questions, 
 wherein each node of the plurality of nodes is indicative of both at least one associated historical issues and at least one solution to the one or more associated historical issues from the clusters of most used prior solutions. 
 
     
     
       2. The method of  claim 1 , further comprising correlating a plurality of solutions to a single issue, wherein a first solution of the plurality of solutions resolves a symptom and a second solution of the plurality of solutions resolves a cause. 
     
     
       3. The method of  claim 1 , further comprising:
 generating an issue summary of the historical issues in a textual chart from recognition of the historical issues and the most used prior solutions; and 
 generating the issue summary in a vector format. 
 
     
     
       4. The method of  claim 3 , wherein the issue summary includes a title, a symptom, a cause, and a resolution. 
     
     
       5. The method of  claim 4 , wherein a first node of the plurality of nodes on the support tree comprises a plurality of related topics, and wherein deflecting from the first node to a second node reduces a field of potential issues and potential issue solutions to the potential issues. 
     
     
       6. The method of  claim 4 , further comprising:
 generating a plurality of potential questions for the user based on the issue summary; 
 providing the issue summary and the plurality of potential questions to an expert; and 
 receiving the plurality of questions from the expert to be presented to the user at each node of the support tree. 
 
     
     
       7. The method of  claim 1 , wherein the clusters are generated by non-negative matrix factorization. 
     
     
       8. The method of  claim 1 , further comprising:
 receiving issue data indicative of a user issue from a client device of the user; 
 identifying a first cluster of nodes, corresponding to the user issue, in the support tree; 
 providing the associated question for the first cluster of nodes to the user to obtain the issue information indicative of the user issue; 
 traversing the support tree from the first cluster of nodes to a second cluster of nodes based on the issue information provided by the user in response to the one or more questions; and 
 providing the one or more solutions to the user to resolve the user issue. 
 
     
     
       9. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by a processor, perform a method of comprising:
 obtaining historical data comprising a history of support interactions including historical issues and prior solutions to the historical issues; 
 determining a number of most used prior solutions from the prior solutions to the historical issues; 
 determining correlations between the most used prior solutions; 
 generating clusters of the most used prior solutions and one or more associated historical issues; 
 determining keywords from the historical issues and associated most used prior solutions; 
 
       generating labels for each cluster based on the determined keywords; 
       generating a plurality of questions to be presented to a user to obtain issue information from the user, each question associated with at least one cluster; and
 automatically generating a support tree comprising a plurality of clusters of nodes, each cluster containing a plurality of nodes, a label for the cluster from the generated labels, and an associated question of the plurality of questions, 
 wherein each node of the plurality of nodes is indicative of both at least one associated historical issues and at least one solution to the one or more associated historical issues from the clusters of most used prior solutions. 
 
     
     
       10. The media of  claim 9 , wherein the computer-executable instructions are further executed to perform:
 receiving issue data indicative of a user issue from a client device of the user; 
 providing one or more questions of the plurality of questions to the user to obtain the issue information indicative of the user issue; 
 deflecting between nodes on the support tree to reduce a field of possible solutions based on the issue information provided by the user in response to the one or more questions; and 
 providing the one or more solutions to the user to resolve the user issue. 
 
     
     
       11. The media of  claim 9 , wherein the computer-executable instructions are further executed to perform correlating a plurality of solutions to a single issue, wherein a first solution of the plurality of solutions resolves a symptom and a second solution of the plurality of solutions resolves a cause. 
     
     
       12. The media of  claim 9 , wherein the computer-executable instructions are further executed to perform:
 generating a plurality of potential questions for the user; 
 providing the plurality of potential questions to an expert; and 
 receiving the plurality of questions from the expert to be presented to the user at each node of the support tree. 
 
     
     
       13. The media of  claim 9 , wherein the clusters are generated by non-negative matrix factorization. 
     
     
       14. The media of  claim 9 , wherein the computer-executable instructions are further executed to perform:
 generating an issue summary of the historical issues in a textual chart from recognition of the historical issues and the most used prior solutions; and 
 generating the issue summary in a vector format. 
 
     
     
       15. The media of  claim 14 , wherein the issue summary includes a title, a symptom, a cause, and a resolution. 
     
     
       16. A system comprising:
 a processor; 
 one or more non-transitory computer-readable media storing computer-executable instructions that, when executed by a processor, perform operations for generating a support tree for automated resolution of user issues, the operations comprising: 
 obtaining historical data comprising a history of support interactions including historical issues and prior solutions to the historical issues; 
 determining a number of most used prior solutions from the prior solutions to the historical issues; 
 determining correlations between the most used prior solutions; 
 generating clusters of the most used prior solutions and one or more associated historical issues; 
 determining keywords from the historical issues and associated most used prior solutions; 
 generating labels for each cluster based on the determined keywords; 
 generating a plurality of questions to be presented to a user to obtain issue information from the user, each question associated with at least one cluster; and 
 automatically generating a support tree comprising a plurality of clusters of nodes, each cluster containing a plurality of nodes, a label for the cluster from the generated labels, and an associated question of the plurality of questions, 
 wherein each node of the plurality of nodes is indicative of both at least one associated historical issues and at least one solution to the one or more associated historical issues from the clusters of most used solutions. 
 
     
     
       17. The system of  claim 16 , wherein the computer-executable instructions are further executed to perform correlating a plurality of solutions to a single issue, wherein a first solution of the plurality of solutions resolves a symptom and a second solution of the plurality of solutions resolves a cause. 
     
     
       18. The system of  claim 16 , wherein the computer-executable instructions are further executed to perform:
 generating a plurality of potential questions for the user; 
 providing the plurality of potential questions to an expert; and 
 receiving the plurality of questions from the expert to be presented to the user at each node of the support tree. 
 
     
     
       19. The system of  claim 16 , wherein the computer-executable instructions are further executed to perform:
 generating an issue summary of the historical issues in a textual chart from recognition of the historical issues and the most used prior solutions; and 
 generating the issue summary in a vector format. 
 
     
     
       20. The system of  claim 19 , wherein the issue summary includes a title, a symptom, a cause, and a resolution.